A Hybrid Framework for Song Lyric Annotation Based on Human-LLM Alignment

• URL: http://arxiv.org/abs/2606.29273v1
• Date: Sun, 28 Jun 2026 08:41:19 GMT
• Title: A Hybrid Framework for Song Lyric Annotation Based on Human-LLM Alignment
• Abstract summary: Emotion recognition of song lyrics is a challenging task since lyrics may not necessarily align with the overall emotion of a song.<n>We examine the alignment between humans and large language model (LLM) assisted annotation by creating a new sentence-level dataset of lyrics.<n>Our observations highlight the subjectivity of the task and the inherent challenges.
• Score: 12.78850268922145
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Emotion recognition of song lyrics is a challenging task since lyrics may not necessarily align with the overall emotion of a song. As a result, lyrics annotation remains largely underexplored. Drawing inspiration from research in large language model (LLM) assisted annotation, we examine the alignment between humans and LLMs for annotation of lyrics by creating a new sentence-level dataset of lyrics. Our observations highlight the subjectivity of the task and the inherent challenges. Following this, we present a hybrid annotation framework that optimizes human and LLM annotation by predicting potential misalignment in annotation.

Related papers

• SongSage: A Large Musical Language Model with Lyric Generative Pre-training [69.52790104805794]
  SongSage is a large musical language model equipped with diverse lyric-centric intelligence through lyric generative pretraining.<n>SongSage exhibits a strong understanding of lyric-centric knowledge, excels in rewriting user queries for zero-shot playlist recommendations, generates and continues lyrics effectively, and performs proficiently across seven additional capabilities.
  arXiv  Detail & Related papers  (2026-01-03T10:54:37Z)
• From Joy to Fear: A Benchmark of Emotion Estimation in Pop Song Lyrics [40.12543056558646]
  The emotional content of song lyrics plays a pivotal role in shaping listener experiences and influencing musical preferences.<n>This paper investigates the task of multi-label emotional attribution of song lyrics by predicting six emotional intensity scores corresponding to six fundamental emotions.
  arXiv  Detail & Related papers  (2025-09-06T06:28:28Z)
• REFFLY: Melody-Constrained Lyrics Editing Model [50.03960548399128]
  This paper introduces REFFLY, the first revision framework for editing and generating melody-aligned lyrics.<n>We train the lyric revision module using our synthesized melody-aligned lyrics dataset.<n>To further enhance the revision ability, we propose training-frees aimed at preserving both semantic meaning and musical consistency.
  arXiv  Detail & Related papers  (2024-08-30T23:22:34Z)
• Towards Estimating Personal Values in Song Lyrics [5.170818712089796]
  Most music widely consumed in Western Countries contains song lyrics, with U.S. samples reporting almost all of their song libraries contain lyrics. In this project, we take a perspectivist approach, guided by social science theory, to gathering annotations, estimating their quality, and aggregating them. We then compare aggregated ratings to estimates based on pre-trained sentence/word embedding models by employing a validated value dictionary.
  arXiv  Detail & Related papers  (2024-08-22T19:22:55Z)
• MuDiT & MuSiT: Alignment with Colloquial Expression in Description-to-Song Generation [18.181382408551574]
  We propose a novel task of Colloquial Description-to-Song Generation. It focuses on aligning the generated content with colloquial human expressions. This task is aimed at bridging the gap between colloquial language understanding and auditory expression within an AI model.
  arXiv  Detail & Related papers  (2024-07-03T15:12:36Z)
• SongComposer: A Large Language Model for Lyric and Melody Generation in Song Composition [82.38021790213752]
  SongComposer is a music-specialized large language model (LLM)<n>It integrates the capability of simultaneously composing melodies into LLMs by leveraging three key innovations.<n>It outperforms advanced LLMs in tasks such as lyric-to-melody generation, melody-to-lyric generation, song continuation, and text-to-song creation.<n>We will release SongCompose, a large-scale dataset for training, containing paired lyrics and melodies in Chinese and English.
  arXiv  Detail & Related papers  (2024-02-27T16:15:28Z)
• Unsupervised Melody-to-Lyric Generation [91.29447272400826]
  We propose a method for generating high-quality lyrics without training on any aligned melody-lyric data. We leverage the segmentation and rhythm alignment between melody and lyrics to compile the given melody into decoding constraints. Our model can generate high-quality lyrics that are more on-topic, singable, intelligible, and coherent than strong baselines.
  arXiv  Detail & Related papers  (2023-05-30T17:20:25Z)
• Unsupervised Melody-Guided Lyrics Generation [84.22469652275714]
  We propose to generate pleasantly listenable lyrics without training on melody-lyric aligned data. We leverage the crucial alignments between melody and lyrics and compile the given melody into constraints to guide the generation process.
  arXiv  Detail & Related papers  (2023-05-12T20:57:20Z)
• Deep Attention-Based Alignment Network for Melody Generation from Incomplete Lyrics [12.05359079565586]
  A deep neural lyrics-to-melody net is trained in an encoder-decoder way to predict possible pairs of lyrics-melody when given incomplete lyrics. The attention mechanism is exploited to align the predicted lyrics with the melody during the lyrics-to-melody generation.
  arXiv  Detail & Related papers  (2023-01-23T03:41:53Z)
• Modelling Emotion Dynamics in Song Lyrics with State Space Models [4.18804572788063]
  We propose a method to predict emotion dynamics in song lyrics without song-level supervision. Our experiments show that applying our method consistently improves the performance of sentence-level baselines without requiring any annotated songs.
  arXiv  Detail & Related papers  (2022-10-17T21:07:23Z)
• Annotation Curricula to Implicitly Train Non-Expert Annotators [56.67768938052715]
  voluntary studies often require annotators to familiarize themselves with the task, its annotation scheme, and the data domain. This can be overwhelming in the beginning, mentally taxing, and induce errors into the resulting annotations. We propose annotation curricula, a novel approach to implicitly train annotators.
  arXiv  Detail & Related papers  (2021-06-04T09:48:28Z)
• SongMASS: Automatic Song Writing with Pre-training and Alignment Constraint [54.012194728496155]
  SongMASS is proposed to overcome the challenges of lyric-to-melody generation and melody-to-lyric generation. It leverages masked sequence to sequence (MASS) pre-training and attention based alignment modeling. We show that SongMASS generates lyric and melody with significantly better quality than the baseline method.
  arXiv  Detail & Related papers  (2020-12-09T16:56:59Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.